Wyniki wyszukiwania - Biblioteka Nauki

Ten serwis zostanie wyłączony 2025-02-11.

Nowa wersja platformy, zawierająca wyłącznie zasoby pełnotekstowe, jest już dostępna.
Przejdź na https://bibliotekanauki.pl

Ograniczanie wyników

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Wyszukiwano:
w słowach kluczowych: facial recognition

Sortuj według:

Ogranicz wyniki do:

Aplikacja demonstrująca identyfikację osób w obrazie ruchomym

100%

Sobczak M.

tom nr 5-6

X-XIV

Do budowy demonstratora wykorzystano aplikację "Multiple face detection and recognition in real time". Jest ona łatwa w instalacji i obsłudze. Bez problemu wykrywa każdą kamerę USB podłączoną do komputera. Dzięki możliwości zmiany kodu możliwe jest dopasowanie rozdzielczości w aplikacji do tej, którą obsługuje kamera.

For the construction of the demonstrator the multiple face detection and recognition in real time application was used. It is easily installable and very handy; it tracks down all USB cameras connected to the computer with no problem. Thanks to the possibility of code changing you can match application resolution to the one being in operation in the camera.

Hybrid end-to-end approach integrating online learning with face-identification system

100%

Nguyene D. V. , Nguyen S. T. , Pham T. H. A. , Pham V. T. , Hoang T. T. , Thanh T. M.

tom T. 24 (2)

141--161

Facial recognition has been one of the most intriguing and exciting research topics over the last few years. It involves multiple face-based algorithms such asfacial detection, facial alignment, facial representation, and facial recognition. However, all of these algorithms are derived from large deep-learning architectures, leading to limitations in development, scalability, accuracy, and deployment for public use with mere CPU servers. Also, large data sets that contain hundreds of thousands of records are often required for training purposes. In this paper, we propose a complete pipeline for an effective face-recognition application that requires only a small data set of Vietnamese celebrities and a CPU for training, solving the problem of data leakage, and the need for GPU devices. The pipeline is based on the combination of a conversion algorithm from face vectors to string tokens and the indexing & retrieval process by Elasticsearch, thereby tackling the problem of online learning in facial recognition. Compared with other popular algorithms on the same data set, our proposed pipeline not only outperforms the counterpart in terms of accuracy but also delivers faster inference, which is essential to real-time applications.